{"slug": "mgdt-mllm-guided-diffusion-transformer-with-relation-adaptive-mixture-of-experts", "title": "MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion", "summary": "Researchers propose MGDT, a novel framework for Multimodal Knowledge Graph Completion that uses a Relation-Adaptive Semantic Routing Mixture-of-Experts module to select relation-relevant multimodal features and a frozen Multimodal Large Language Model as a semantic anchor, outperforming strong baselines on three benchmark datasets.", "body_md": "arXiv:2607.15592v1 Announce Type: new\nAbstract: Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to simultaneously perform relation-dependent cue selection, cross-modal semantic alignment, and structure-aware entity generation, which introduces noisy and semantically inconsistent conditions for diffusion and consequently leads to suboptimal completion performance. To address this limitation, we propose MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts (MGDT), a novel MKGC framework built on an align-then-diffuse paradigm. MGDT first employs a Relation-Adaptive Semantic Routing Mixture-of-Experts (RASR-MoE) module to select relation-relevant multimodal semantic transformation paths and suppress irrelevant modality interference. MGDT then uses a frozen Multimodal Large Language Model (MLLM) as a semantic anchor to align the routed multimodal representations into a unified latent space and reduce cross-modal semantic heterogeneity. Finally, a Knowledge Graph Diffusion Transformer (KGDT) performs graph-conditioned denoising generation in the aligned space to produce the missing entity representation. Experiments on three benchmark datasets show that MGDT consistently outperforms strong baselines.", "url": "https://wpnews.pro/news/mgdt-mllm-guided-diffusion-transformer-with-relation-adaptive-mixture-of-experts", "canonical_source": "https://arxiv.org/abs/2607.15592", "published_at": "2026-07-20 04:00:00+00:00", "updated_at": "2026-07-20 13:53:12.203725+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning"], "entities": ["MGDT", "RASR-MoE", "KGDT"], "alternates": {"html": "https://wpnews.pro/news/mgdt-mllm-guided-diffusion-transformer-with-relation-adaptive-mixture-of-experts", "markdown": "https://wpnews.pro/news/mgdt-mllm-guided-diffusion-transformer-with-relation-adaptive-mixture-of-experts.md", "text": "https://wpnews.pro/news/mgdt-mllm-guided-diffusion-transformer-with-relation-adaptive-mixture-of-experts.txt", "jsonld": "https://wpnews.pro/news/mgdt-mllm-guided-diffusion-transformer-with-relation-adaptive-mixture-of-experts.jsonld"}}